stitch-vue-element-components

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes a bash script (scripts/fetch-stitch.sh) to download design HTML from URLs provided by the Stitch MCP. This is a functional requirement for accessing design assets stored in cloud buckets.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to run the local 'fetch-stitch.sh' script, which employs curl to ensure high-reliability downloads by handling redirects and TLS.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes external HTML and JSON design data. 1. Ingestion points: temp/source.html and Stitch MCP metadata. 2. Boundary markers: Absent. 3. Capability inventory: Bash, Write, Read, and web_fetch. 4. Sanitization: Absent. The agent relies on internal architectural rules to guide the conversion process safely.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 04:05 PM
Security Audit — agent-trust-hub — stitch-vue-element-components